That's "dictionary" compression still. AI checks for hints to lookup in well... dictionary. If the dictionary changes, your compression results change too.
Silly Image Compression Idea
21–30 of 59 posts
Re: Silly Image Compression Idea
#22While not exactly the idea in your post, this recent paper by Dubois, Bloem-Reddy, Ullrich, and Maddison on "Lossy Compression for Lossless Prediction" (https://arxiv.org/abs/2106.10800) kinda gets at this idea.
From the abstract:
Most data is automatically collected and only ever "seen" by algorithms. Yet, data compressors preserve perceptual fidelity rather than just the information needed by algorithms performing downstream tasks. In this paper, we characterize the bit-rate required to ensure high performance on all predictive tasks that are invariant under a set of transformations, such as data augmentations...
Using these objectives, we train a generic image compressor that achieves substantial rate savings (more than 1000× on ImageNet) compared to JPEG on 8 datasets, without decreasing downstream classification performance.
Pretty cool stuff!
Re: Silly Image Compression Idea
#23A sort-of related idea is: How small can an image of a human face be and still be recognizable? I remember X-face images from mail headers years ago -- these were just 48 x 48 x 1 pixel images, i.e., just 288 bytes (yes, bytes, not KB or MB). I marveled that the faces were indeed recognizable. I wish I could find an example of an X-face of a famous person (or even an unknown person) to give as an example here, but this seems to be one of those things that are ungoogleable.
Re: Silly Image Compression Idea
#24A sort-of related idea is: How small can an image of a human face be and still be recognizable? I remember X-face images from mail headers years ago -- these were just 48 x 48 x 1 pixel images, i.e., just 288 bytes (yes, bytes, not KB or MB). I marveled that the faces were indeed recognizable. I wish I could find an example of an X-face of a famous person (or even an unknown person) to give as an example here, but th…
After some digging ("x-face image usenet" on DDG yielded a link to a page on curlie.org), I found this collection: https://ace.home.xs4all.nl/X-Faces/
Re: Silly Image Compression Idea
#25Compression with no plan in sight for decompression... at least it's billed as "silly" first and foremost.
I've seen worse; someone presented code for decompression of a fictional data format with no plan in sight for compression. When I asked how the compression part would be implemented, the author called me stupid for asking this question and told me the project was inspired by https://en.wikipedia.org/wiki/Sloot_Digital_Coding_System
Reminds me when I as a 14 year old, barely two years after I started learning programming and having just learned about cyclic redundancy check (CRC), wondered why they couldn't be used for compression. Take a block of say 16 bytes, calculate the CRC code and store that.
To decompress you then just had to find the string of bytes that generated a matching CRC code.
It seemed so brilliant, but something told me it was too good to be true, and surely someone would have come up with this before me... So I tried figuring out why it wouldn't work. Still, took me a day or so before I figured out how long "just" was and that collisions would render it moot anyway.
Learned a lot from that though, as an aspiring programmer.
Re: Silly Image Compression Idea
#26Why stop at the 'AI's limit? We can do better than that. Keep going until a human can no longer recognise the image! (There's always a mechanical Turk to do the work.)
And why stop when the image is unrecognisable? Why not translate the image of (say) a cat into an image of the word 'cat'? And if you've done that compression, take it a step further - translate the image of the cat into the text string 'cat'. Now you're getting seriously good compression ratios :)
Re: Silly Image Compression Idea
#27Why stop at the 'AI's limit? We can do better than that. Keep going until a human can no longer recognise the image! (There's always a mechanical Turk to do the work.) And why stop when the image is unrecognisable? Why not translate the image of (say) a cat into an image of the word 'cat'? And if you've done that compression, take it a step further - translate the image of the cat into the text string 'cat'. Now you'…
A long time ago I thought that this kind of compression could be interesting for voice chat/phone calls. Locally convert speech to text, send raw text over the wire, and convert text back to speech.
You could fine tune some existing text to speech model to sound like you. Once you transfer that to your friends/frequent contacts you could have voice conversations over very low bandwidth channels.
There are obviously plenty of caveats to this, like communicating sounds that aren’t speech. It could be a useful fallback e.g. if your network quality is seriously degraded then your client switches to TTS mode.
Re: Silly Image Compression Idea
#28If I’m not mistaken, this is more generalizable as Silly HashMap Algorithm Idea, which is probably a worthy pursuit. The idea is to find the minimal meaningful key with the highest likelihood of resolving to the correct value. Compression is meaningless to the former but valuable for the latter.
Re: Silly Image Compression Idea
#29Why stop at the 'AI's limit? We can do better than that. Keep going until a human can no longer recognise the image! (There's always a mechanical Turk to do the work.) And why stop when the image is unrecognisable? Why not translate the image of (say) a cat into an image of the word 'cat'? And if you've done that compression, take it a step further - translate the image of the cat into the text string 'cat'. Now you'…
A long time ago I thought that this kind of compression could be interesting for voice chat/phone calls. Locally convert speech to text, send raw text over the wire, and convert text back to speech. You could fine tune some existing text to speech model to sound like you. Once you transfer that to your friends/frequent contacts you could have voice conversations over very low bandwidth channels. There are obviously p…
There are speech codecs that essentially do this but with a phonetic encoding, instead of "normal" text.
Yes, they are only used for extremely bandwidth-starved situations, but they do work. An example is Codec2, which works down to 0.7 kbit/s.
Re: Silly Image Compression Idea
#30Why stop at the 'AI's limit? We can do better than that. Keep going until a human can no longer recognise the image! (There's always a mechanical Turk to do the work.) And why stop when the image is unrecognisable? Why not translate the image of (say) a cat into an image of the word 'cat'? And if you've done that compression, take it a step further - translate the image of the cat into the text string 'cat'. Now you'…
A long time ago I thought that this kind of compression could be interesting for voice chat/phone calls. Locally convert speech to text, send raw text over the wire, and convert text back to speech. You could fine tune some existing text to speech model to sound like you. Once you transfer that to your friends/frequent contacts you could have voice conversations over very low bandwidth channels. There are obviously p…
Well there's already speech-oriented codecs that can go down below a kilobyte per second, and there's this one that throws a neural net at the problem to help squeeze bytes: https://ai.googleblog.com/2021/08/soundstream-end-to-end-neu...
I don't think I've ever had a functional connection slower than that. You need packets to be making it through in a timely manner if you want a voice conversation, after all.